Mercurial > repos > iuc > episcanpy_cluster_embed

changeset 1:f4713992f23a draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/episcanpy/ commit bb79cb8cad3bc1433bff7caf9d7b45e7993dd470
author iuc
date Sat, 22 Apr 2023 12:14:16 +0000
parents 7340d619d7f8
children
files cluster_embed.xml macros.xml test-data/chrY.h5ad test-data/chrY_norm_peaks.h5ad test-data/chrY_with_transcript_annotation.h5ad
diffstat 5 files changed, 6 insertions(+), 86 deletions(-) [+]
line wrap: on
line diff
--- a/cluster_embed.xml	Tue Apr 18 13:19:32 2023 +0000
+++ b/cluster_embed.xml	Sat Apr 22 12:14:16 2023 +0000
@@ -46,16 +46,6 @@
     corr_method='$method.rank_features_corr_method'
     )
 
-#else if $method.method == 'tl.find_genes'
-esc.tl.find_genes(
-    adata,
-    gtf_file='$method.find_genes_gtf_file',
-    key_added='$method.find_genes_key_added',
-    upstream=$method.find_genes_upstream,
-    feature_type='$method.find_genes_feature_type',
-    annotation='$method.find_genes_annotation',
-    raw=$method.find_genes_raw)
-
 #else if $method.method == 'tl.get_n_clusters'
 esc.tl.getNClusters(
     adata,
@@ -88,7 +78,6 @@
             <param argument="method" type="select" label="Method used for Clustering or Embedding">
                 <option value="pp.lazy">Embedding: Automatically compute PCA coordinates, loadings and variance decomposition, a neighborhood graph of observations, t-distributed stochastic neighborhood embedding (tSNE) Uniform Manifold Approximation and Projection (UMAP), using 'pp.lazy'</option>
                 <option value="tl.rank_features">Rank features for characterizing groups, using 'tl.rank_features'</option>
-                <option value="tl.find_genes">Embedding: Find genes and add annotations, using 'pp.find_genes'</option>
                 <option value="tl.get_n_clusters">Clustering: Test different settings of louvain to obtain the target number of clusters, using 'tl.getNClusters'</option>
                 <option value="tl.kmeans">Clustering: Compute kmeans clustering using X_pca fits, using 'tl.kmeans'</option>
                 <option value="tl.hc">Clustering: Compute hierarchical clustering using X_pca fits, using 'tl.hc'</option>
@@ -213,50 +202,6 @@
                     <option value="bonferroni">Bonferroni</option>
                 </param>
             </when>
-            <when value="tl.find_genes">
-                <param name="find_genes_gtf_file" type="data" format="gtf" label="Annotation GTF file" help="(gtf_file)"/>
-                <param name="find_genes_key_added" value="transcript_annotation" type="text" label="Key added" help="(key_added)">
-                    <sanitizer invalid_char="">
-                        <valid initial="string.letters,string.digits">
-                            <add value="_" />
-                            <add value="-" />
-                            <add value="." />
-                            <add value=" " />
-                            <add value="," />
-                        </valid>
-                    </sanitizer>
-                    <validator type="regex">[0-9a-zA-Z_., -]+</validator>
-                </param>
-                <param name="find_genes_upstream" value="2000" min="0" type="integer" label="Upstream" help="(upstream)"/>
-                <param name="find_genes_feature_type" value="transcript" type="text" label="Feature type" help="(feature_type)">
-                    <sanitizer invalid_char="">
-                        <valid initial="string.letters,string.digits">
-                            <add value="_" />
-                            <add value="-" />
-                            <add value="." />
-                            <add value=" " />
-                            <add value="," />
-                        </valid>
-                    </sanitizer>
-                    <validator type="regex">[0-9a-zA-Z_., -]+</validator>
-                </param>
-                <param name="find_genes_annotation" value="HAVANA" type="text" label="Annotation" help="(annotation)">
-                    <sanitizer invalid_char="">
-                        <valid initial="string.letters,string.digits">
-                            <add value="_" />
-                            <add value="-" />
-                            <add value="." />
-                            <add value=" " />
-                            <add value="," />
-                        </valid>
-                    </sanitizer>
-                    <validator type="regex">[0-9a-zA-Z_., -]+</validator>
-                </param>
-                <param name="find_genes_raw" type="select" label="Raw?" help="(raw)">
-                    <option value="True">True</option>
-                    <option value="False" selected="true">False</option>
-                </param>
-            </when>
             <when value="tl.get_n_clusters">
                 <param name="get_n_clusters_n_cluster" value="14" min="1" type="integer" label="Number of clusters" help="(n_cluster)"/>
                 <param name="get_n_clusters_method" type="select" label="Clustering method to use" help="(method)">
@@ -293,7 +238,7 @@
     </outputs>
     <tests>
         <test expect_num_outputs="2">
-            <!-- test 0- pp.lazy -->
+            <!-- pp.lazy -->
             <param name="adata" value="krumsiek11.h5ad" />
             <conditional name="method">
                 <param name="method" value="pp.lazy"/>
@@ -322,7 +267,7 @@
             <output name="anndata_out" file="krumsiek11.pp.lazy.h5ad" ftype="h5ad" compare="sim_size"/>
         </test>
         <test expect_num_outputs="2">
-            <!-- test 1- tl.rank_features -->
+            <!-- tl.rank_features -->
             <param name="adata" value="krumsiek11.pp.lazy.tl.louvain.h5ad" />
             <conditional name="method">
                 <param name="method" value="tl.rank_features"/>
@@ -345,29 +290,8 @@
                 </assert_contents>
             </output>
         </test>
-       <test expect_num_outputs="2">
-           <!-- test 2-tl.find_genes -->
-           <param name="adata" value="chrY.h5ad" />
-           <conditional name="method">
-               <param name="method" value="tl.find_genes"/>
-               <param name="find_genes_gtf_file" value="chrY.gtf"/>
-               <param name="find_genes_key_added" value="transcript_annotation"/>
-               <param name="find_genes_upstream" value="2000"/>
-               <param name="find_genes_feature_type" value="transcript"/>
-               <param name="find_genes_annotation" value="HAVANA"/>
-               <param name="find_genes_raw" value="False"/>
-           </conditional>
-           <section name="advanced_common">
-               <param name="show_log" value="true" />
-           </section>
-           <output name="anndata_out" file="chrY_with_transcript_annotation.h5ad" ftype="h5ad" compare="sim_size">
-                <assert_contents>
-                    <has_h5_keys keys="var" />
-                </assert_contents>
-            </output>
-        </test>
         <test expect_num_outputs="2">
-            <!-- test 3-tl.get_n_clusters -->
+            <!-- tl.get_n_clusters -->
             <param name="adata" value="krumsiek11.pp.lazy.tl.louvain.h5ad" />
             <conditional name="method">
                 <param name="method" value="tl.get_n_clusters"/>
@@ -386,7 +310,7 @@
             <output name="anndata_out" file="krumsiek11.tl.get_n_clusters.h5ad" ftype="h5ad"/>
         </test>
         <test expect_num_outputs="2">
-        <!-- test 4-tl.kmeans -->
+        <!-- tl.kmeans -->
             <param name="adata" value="krumsiek11.pp.lazy.h5ad" />
             <conditional name="method">
                 <param name="method" value="tl.kmeans"/>
@@ -398,7 +322,7 @@
             <output name="anndata_out" file="krumsiek11.tl.kmeans.h5ad" ftype="h5ad"/>
         </test>
         <test expect_num_outputs="2">
-        <!-- test 5-tl.hc -->
+        <!-- tl.hc -->
             <param name="adata" value="krumsiek11.pp.lazy.h5ad" />
             <conditional name="method">
                 <param name="method" value="tl.hc"/>
@@ -420,10 +344,6 @@
 More details on the `episcanpy documentation
 <https://colomemaria.github.io/episcanpy_doc/api/episcanpy.api.pp.lazy.html>`__
 
-Find and add gene annotations (`tl.find_genes`)
-========================================================================================
-This function adds a gene annotation to an AnnData (h5ad) file from annotations file (.annotation.gtf).
-
 Automatically obtain target number of clusters (`tl.getNClusters`)
 ========================================================================================
 This function will test different settings of louvain to obtain the target number of clusters.
--- a/macros.xml	Tue Apr 18 13:19:32 2023 +0000
+++ b/macros.xml	Sat Apr 22 12:14:16 2023 +0000
@@ -1,6 +1,6 @@
 <macros>
     <token name="@TOOL_VERSION@">0.3.2</token>
-    <token name="@VERSION_SUFFIX@">0</token>
+    <token name="@VERSION_SUFFIX@">1</token>
     <token name="@PROFILE@">21.01</token>
     <xml name="requirements">
         <requirements>
Binary file test-data/chrY.h5ad has changed
Binary file test-data/chrY_norm_peaks.h5ad has changed
Binary file test-data/chrY_with_transcript_annotation.h5ad has changed